© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 5058
    Prev
    Next
    INDEX
    Explanations

    sameness of meaning

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.3-70B-IT @ 50-resid-post-gf
    Configuration
    Goodfire/Llama-3.3-70B-Instruct-SAE-l50/Llama-3.3-70B-Instruct-SAE-l50.pt
    Prompts (Dashboard)
    10,000 prompts, 128 tokens each
    Dataset (Dashboard)
    lmsys/lmsys-chat-1m
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bserv
    -0.10
     itself
    -0.09
    dap
    -0.09
    å®ļ
    -0.09
    kas
    -0.08
    RelativeTo
    -0.08
    ersive
    -0.08
     ï¾ŀ
    -0.08
    furt
    -0.08
    lbrace
    -0.08
    POSITIVE LOGITS
     identical
    0.23
    缸åIJĮ
    0.19
     same
    0.19
     share
    0.18
     Same
    0.17
     Ident
    0.17
     sharing
    0.17
    Same
    0.17
    same
    0.16
    ident
    0.15
    Activations Density 0.215%

    No Known Activations